Simple and Scalable Strategies to Continually Pre-train Large Language Models

Open Webpage

Adam Ibrahim, Benjamin Thérien, Kshitij Gupta, Mats L. Richter, Quentin Gregory Anthony, Eugene Belilovsky, Timothée Lesort, Irina Rish

Published: 01 Jan 2024, Last Modified: 18 May 2025Trans. Mach. Learn. Res. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0